# @repligate — 2023-10-19

♥56 ↻3 · https://x.com/repligate/status/1715100073393029137

@AtillaYasar69 That models are able to retrieve their stop token based on semantic pointer kinda disturbing, like it's integrated with the rest of their world knowledge. Does this mean they also know in some sense that it's LLM training data they're seeing every time they see it at training?

tags: author:repligate, kind:tweet, thread-context, year:2023